Abstract
Movement behavior models of pedestrian agents form the basis of computational crowd simulations. In contemporary research, a large number of models exist. However, there is still no walking behavior model that can address the various influence factors of movement behavior holistically. Thus, we endorse the use of artificial neural networks to develop walking behavior models because machine learning methods can integrate behavioral factors efficiently, automatically, and data-driven. In this paper, we support this approach by providing a framework that describes how to include artificial neural networks into a pedestrian research context. The framework comprises 5 phases: data, replay, training, simulation, and validation. Furthermore, we describe and discuss a prototype of the framework.
Highlights
The research on pedestrian walking properties identified various influence factors on movement behavior
We developed a framework that embeds the artificial neural network (ANN) methodology in the pedestrian research domain
We point to the literature for further reading as the focus of this paper is to provide a framework that embeds an ANN in a pedestrian dynamics context
Summary
The research on pedestrian walking properties identified various influence factors on movement behavior. The sensing data comprises the relative distance and velocity of the 5 nearest pedestrians in front of a pedestrian agent These papers showed that it is possible to apply ANNs in a pedestrian dynamics environment to simulate operational behavior. We define a framework that embeds an ANN for walking behavior modeling and simulation This framework is a useful guideline for pedestrian dynamics researchers that like to include ANNs in their methods. Integrating artificial neural networks in pedestrian research we provide the details on the developed framework and discuss a prototype implementation of the method In this context, we show a case study using data from a laboratory experiment. Well-known methods for model validation are applied to evaluate the capabilities of the developed ANN model
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.